Solr MCP Server

A Spring AI Model Context Protocol (MCP) server that provides tools for interacting with Apache Solr. This server enables AI assistants like Claude to search, index, and manage Solr collections through the MCP protocol.

Overview

This project provides a set of tools that allow AI assistants to interact with Apache Solr, a powerful open-source search platform. By implementing the Spring AI MCP protocol, these tools can be used by any MCP-compatible client, including Claude Desktop. The project uses SolrJ, the official Java client for Solr, to communicate with Solr instances.

The server provides the following capabilities:

• Search Solr collections with advanced query options
• Index documents into Solr collections
• Manage and monitor Solr collections
• Retrieve and analyze Solr schema information

Transport Profiles

The server supports two transport modes:

• STDIO (Standard Input/Output) - Recommended for local development and production use with Claude Desktop. This is the default and most secure option for local deployments.
• HTTP (Streamable HTTP) - For testing with MCP Inspector and remote deployments. ⚠️ Note: HTTP mode is inherently insecure without additional security measures (see Security Considerations below).

Prerequisites

• Java 25 or higher
• Docker and Docker Compose (for running Solr)
• Gradle 9.1.0+ (wrapper included in project)

Installation and Setup

1. Clone the repository

git clone https://github.com/yourusername/solr-mcp-server.git
cd solr-mcp-server

2. Start Solr using Docker Compose

docker-compose up -d

This will start a Solr instance in SolrCloud mode with ZooKeeper and create two sample collections:

• books - A collection with sample book data
• films - A collection with sample film data

3. Build the Project

This project uses Gradle with version catalogs for dependency management. All dependencies and their versions are centrally managed in gradle/libs.versions.toml.

# Build the project and run tests
./gradlew build

# Build without tests (faster)
./gradlew assemble

# Clean and rebuild
./gradlew clean build

The build produces two JAR files in build/libs/:

• solr-mcp-server-0.0.1-SNAPSHOT.jar - Executable JAR with all dependencies (fat JAR)
• solr-mcp-server-0.0.1-SNAPSHOT-plain.jar - Plain JAR without dependencies

Project Structure

The codebase follows a clean, modular architecture organized by functionality:

src/main/java/org/apache/solr/mcp/server/
├── Main.java                           # Application entry point
├── config/                             # Configuration classes
│   ├── SolrConfig.java                # Solr client bean configuration
│   └── SolrConfigurationProperties.java # Solr connection properties
├── search/                             # Search functionality
│   ├── SearchService.java             # MCP tool for searching Solr
│   └── SearchResponse.java            # Search result DTOs
├── indexing/                           # Document indexing functionality
│   ├── IndexingService.java           # MCP tool for indexing documents
│   └── documentcreator/               # Document format parsers
│       ├── IndexingDocumentCreator.java    # Interface for document creators
│       ├── JsonDocumentCreator.java        # JSON document parser
│       ├── CsvDocumentCreator.java         # CSV document parser
│       ├── XmlDocumentCreator.java         # XML document parser
│       ├── SolrDocumentCreator.java        # Factory for document creators
│       ├── FieldNameSanitizer.java         # Field name sanitization utility
│       └── DocumentProcessingException.java # Indexing exceptions
└── metadata/                           # Collection management functionality
    ├── CollectionService.java         # MCP tools for collection operations
    ├── SchemaService.java             # MCP tool for schema retrieval
    ├── CollectionUtils.java           # Colle

... [View full README on GitHub](https://github.com/adityamparikh/solr-mcp-server#readme)